Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code or machine learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lfw
    -0.06
    's
    -0.06
     cancellation
    -0.06
    _GRAPH
    -0.06
    aned
    -0.06
    Value
    -0.06
    aking
    -0.06
     Keto
    -0.06
    ίας
    -0.06
    .backup
    -0.06
    POSITIVE LOGITS
     نسب
    0.07
     obliv
    0.07
     elemento
    0.06
     сьогодні
    0.06
    .AutoScaleDimensions
    0.06
            ↵↵
    0.06
     захворювання
    0.06
     rewind
    0.06
     cres
    0.06
     fest
    0.06
    Act Density 0.049%

    No Known Activations